Aero Hand Open: A Simulation-Ready Tendon-Driven Hand for Dexterous Manipulation Learning
2026-08-28 • Robotics
RoboticsArtificial IntelligenceMachine Learning
AI summaryⓘ
The authors present Aero Hand Open, a robotic hand that uses cables to move fingers, making it cheaper and simpler than hands with motors at each joint. They explain that using cables means fewer and smaller motors are needed, but it makes the hand harder to control and simulate. To solve this, the authors provide a detailed computer model and training tools that let a robot learn to use the hand in simulation before controlling the real hand without extra adjustments. They share everything needed, like designs and software, to help others build and train this type of robotic hand.
tendon-driven handanthropomorphic robotunderactuationcable transmissionmotor actuationrobot simulationreinforcement learningrobot control policiesrobotic hand design
Authors
Nan Wang, Mohit Yadav, Jonathan Wulff, Aidan Rosenbaum, Kezhou Chen, Yuvan Sharma, Xu Dong, Yiwei Tao
Abstract
Tendon-driven hands are anthropomorphic, and moving the actuators off the joints is what makes a hand of this capability affordable to build. Two effects produce that saving. Routing force through a cable removes the requirement that a motor fit inside the joint it drives, so smaller and cheaper motors suffice, and one motor can drive several joints through a single cable, so fewer motors are needed. They are also harder to learn on than a direct-drive hand. The underactuated transmission that produces the saving is itself difficult to represent in a simulator, and the joints one cable drives are not independently commandable. We present Aero Hand Open, a tendon-driven anthropomorphic hand that is released simulation-ready. Three things ship with it. A simulation model reproduces the cable transmission itself. An identified actuation map connects that model to the motor commands in both directions, including the three-way coupling of the thumb. A reinforcement learning package trains policies for the hand. Together they let a policy be trained entirely in simulation and run on the hand with no fine-tuning and no state estimation. We release the mechanical design, the simulation model, the identified mapping, the training environment and the deployment stack.